Enhanced Fish Freshness Classification with Incremental Handcrafted Feature Fusion

2025-10-20

AI Summary

Fish freshness assessment suffers from subjectivity, poor reproducibility, and limited cross-species generalizability. To address these challenges, this paper proposes an incremental feature fusion classification framework based on fish-eye images. It systematically extracts handcrafted features—including color statistics, multi-color-space histograms, Local Binary Patterns (LBP), and Gray-Level Co-occurrence Matrix (GLCM) texture descriptors—and incrementally fuses global and local region information to enhance both interpretability and discriminative power. The method integrates LightGBM and Artificial Neural Network (ANN) classifiers, augmented with tailored data augmentation strategies. Evaluated on the FFE dataset, LightGBM achieves 77.56% accuracy—surpassing deep learning baselines by 14.35%—while ANN attains 97.16% accuracy, outperforming prior state-of-the-art by 19.86%. These results demonstrate the substantial advantages of carefully engineered handcrafted features in low-data, high-interpretability scenarios.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Normalization, clustering, classification, and summarization of Web text
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Accurate assessment of fish freshness remains a major challenge in the food industry, with direct consequences for product quality, market value, and consumer health. Conventional sensory evaluation is inherently subjective, inconsistent, and difficult to standardize across contexts, often limited by subtle, species-dependent spoilage cues. To address these limitations, we propose a handcrafted feature-based approach that systematically extracts and incrementally fuses complementary descriptors, including color statistics, histograms across multiple color spaces, and texture features such as Local Binary Patterns (LBP) and Gray-Level Co-occurrence Matrices (GLCM), from fish eye images. Our method captures global chromatic variations from full images and localized degradations from ROI segments, fusing each independently to evaluate their effectiveness in assessing freshness. Experiments on the Freshness of the Fish Eyes (FFE) dataset demonstrate the approach's effectiveness: in a standard train-test setting, a LightGBM classifier achieved 77.56% accuracy, a 14.35% improvement over the previous deep learning baseline of 63.21%. With augmented data, an Artificial Neural Network (ANN) reached 97.16% accuracy, surpassing the prior best of 77.3% by 19.86%. These results demonstrate that carefully engineered, handcrafted features, when strategically processed, yield a robust, interpretable, and reliable solution for automated fish freshness assessment, providing valuable insights for practical applications in food quality monitoring.

Problem

• Automating fish freshness classification using handcrafted feature fusion
• Overcoming subjective sensory evaluation with computer vision techniques
• Improving accuracy through multi-feature extraction from fish eye images

Innovation

• Handcrafted feature fusion from fish eye images
• Combining color statistics and texture descriptors
• Incremental feature processing for freshness classification